Llama 3.2 90B Vision Instruct

Meta's instruction-tuned vision-language model supports image captioning, visual questions and document understanding. It connects a separately trained vision adapter to a Llama 3.1 language model through cross-attention layers.

CONTEXT128K

MAX OUTPUT8K

LAST SCAN13 Nov 2026

Open weights TextImage

Free aggregator routes

These are the aggregator routes recorded in the current or last published catalog. Each route keeps its exact model ID and thinking information.

The supplied successful test at 2026-11-05T18:53:05+00:00 establishes access to this exact NVIDIA route without a top-up using the dedicated account that had never held credit or linked a payment method. Continued availability and quotas are not established.

Limits above: NVIDIA. Available gateway routes are listed below.

NVIDIA's exact route reference identifies Meta's Llama-3.2-90B-Vision-Instruct, corresponding to the creator repository meta-llama/Llama-3.2-90B-Vision-Instruct. This identifies the instruction-tuned 90B vision release rather than its base or 11B variants. No pinned serving revision is established.

NVIDIA

Info

Thinking: Not advertised by this API

Model ID · NVIDIA APImeta/llama-3.2-90b-vision-instruct

Model sources

Use it through LiteLLM

Import the current LiteLLM-compatible YAML and use the exact model ID shown above. The catalog is generated from the same reviewed scan data as the download.

Download LiteLLM YAML